Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning?
Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification usi...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0269016 |
| _version_ | 1818491023992553472 |
|---|---|
| author | Shintaro Sukegawa Kazumasa Yoshii Takeshi Hara Futa Tanaka Katsusuke Yamashita Tutaro Kagaya Keisuke Nakano Kiyofumi Takabatake Hotaka Kawai Hitoshi Nagatsuka Yoshihiko Furuki |
| author_facet | Shintaro Sukegawa Kazumasa Yoshii Takeshi Hara Futa Tanaka Katsusuke Yamashita Tutaro Kagaya Keisuke Nakano Kiyofumi Takabatake Hotaka Kawai Hitoshi Nagatsuka Yoshihiko Furuki |
| author_sort | Shintaro Sukegawa |
| collection | DOAJ |
| description | Attention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to "Huge" for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models. |
| first_indexed | 2024-12-10T17:24:46Z |
| format | Article |
| id | doaj.art-af5f8d9a9e9648dcb9df54fb6e71521c |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-10T17:24:46Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-af5f8d9a9e9648dcb9df54fb6e71521c2022-12-22T01:39:53ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01177e026901610.1371/journal.pone.0269016Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning?Shintaro SukegawaKazumasa YoshiiTakeshi HaraFuta TanakaKatsusuke YamashitaTutaro KagayaKeisuke NakanoKiyofumi TakabatakeHotaka KawaiHitoshi NagatsukaYoshihiko FurukiAttention mechanism, which is a means of determining which part of the forced data is emphasized, has attracted attention in various fields of deep learning in recent years. The purpose of this study was to evaluate the performance of the attention branch network (ABN) for implant classification using convolutional neural networks (CNNs). The data consisted of 10191 dental implant images from 13 implant brands that cropped the site, including dental implants as pretreatment, from digital panoramic radiographs of patients who underwent surgery at Kagawa Prefectural Central Hospital between 2005 and 2021. ResNet 18, 50, and 152 were evaluated as CNN models that were compared with and without the ABN. We used accuracy, precision, recall, specificity, F1 score, and area under the receiver operating characteristics curve as performance metrics. We also performed statistical and effect size evaluations of the 30-time performance metrics of the simple CNNs and the ABN model. ResNet18 with ABN significantly improved the dental implant classification performance for all the performance metrics. Effect sizes were equivalent to "Huge" for all performance metrics. In contrast, the classification performance of ResNet50 and 152 deteriorated by adding the attention mechanism. ResNet18 showed considerably high compatibility with the ABN model in dental implant classification (AUC = 0.9993) despite the small number of parameters. The limitation of this study is that only ResNet was verified as a CNN; further studies are required for other CNN models.https://doi.org/10.1371/journal.pone.0269016 |
| spellingShingle | Shintaro Sukegawa Kazumasa Yoshii Takeshi Hara Futa Tanaka Katsusuke Yamashita Tutaro Kagaya Keisuke Nakano Kiyofumi Takabatake Hotaka Kawai Hitoshi Nagatsuka Yoshihiko Furuki Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? PLoS ONE |
| title | Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? |
| title_full | Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? |
| title_fullStr | Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? |
| title_full_unstemmed | Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? |
| title_short | Is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning? |
| title_sort | is attention branch network effective in classifying dental implants from panoramic radiograph images by deep learning |
| url | https://doi.org/10.1371/journal.pone.0269016 |
| work_keys_str_mv | AT shintarosukegawa isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT kazumasayoshii isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT takeshihara isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT futatanaka isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT katsusukeyamashita isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT tutarokagaya isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT keisukenakano isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT kiyofumitakabatake isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT hotakakawai isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT hitoshinagatsuka isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning AT yoshihikofuruki isattentionbranchnetworkeffectiveinclassifyingdentalimplantsfrompanoramicradiographimagesbydeeplearning |